Skip to main content
Glama
enesjakozh
pyroprompts

any-chat-completions-mcp

by pyroprompts
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Servidor MCP de cualquier chat completado en mcp

Integre Claude con cualquier API de finalización de chat compatible con OpenAI SDK: OpenAI, Perplexity, Groq, xAI, PyroPrompts y más.

Esto implementa el servidor de protocolo de contexto de modelo. Más información: https://modelcontextprotocol.io

Este es un servidor MCP basado en TypeScript que implementa una implementación en cualquier API de finalización de chat compatible con OpenAI SDK.

Tiene una herramienta, chat , que transmite una pregunta a un proveedor de chat de IA configurado.

insignia de herrería

Desarrollo

Instalar dependencias:

npm install

Construir el servidor:

npm run build

Para desarrollo con reconstrucción automática:

npm run watch

Related MCP server: Ultimate-MCP-Server

Instalación

Para agregar OpenAI a Claude Desktop, agregue la configuración del servidor:

En MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

En Windows: %APPDATA%/Claude/claude_desktop_config.json

Puedes usarlo a través de npx en tu configuración de Claude Desktop de esta manera:

{
  "mcpServers": {
    "chat-openai": {
      "command": "npx",
      "args": [
        "@pyroprompts/any-chat-completions-mcp"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
      }
    }
  }
}

O, si clonas el repositorio, puedes compilarlo y usarlo en tu configuración de Claude Desktop de esta manera:


{
  "mcpServers": {
    "chat-openai": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
      }
    }
  }
}

Puede agregar varios proveedores haciendo referencia al mismo servidor MCP varias veces, pero con diferentes argumentos de entorno:


{
  "mcpServers": {
    "chat-pyroprompts": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "PYROPROMPTS_KEY",
        "AI_CHAT_NAME": "PyroPrompts",
        "AI_CHAT_MODEL": "ash",
        "AI_CHAT_BASE_URL": "https://api.pyroprompts.com/openaiv1"
      }
    },
    "chat-perplexity": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "PERPLEXITY_KEY",
        "AI_CHAT_NAME": "Perplexity",
        "AI_CHAT_MODEL": "sonar",
        "AI_CHAT_BASE_URL": "https://api.perplexity.ai"
      }
    },
    "chat-openai": {
      "command": "node",
      "args": [
        "/path/to/any-chat-completions-mcp/build/index.js"
      ],
      "env": {
        "AI_CHAT_KEY": "OPENAI_KEY",
        "AI_CHAT_NAME": "OpenAI",
        "AI_CHAT_MODEL": "gpt-4o",
        "AI_CHAT_BASE_URL": "https://api.openai.com/v1"
      }
    }
  }
}

Con estos tres, verás una herramienta para cada uno en la página de inicio de Claude Desktop:

Claude Desktop Home con herramientas de chat

Y luego puedes chatear con otros LLM y se muestra en el chat de esta manera:

Claude Chat con OpenAI

O bien, configúrelo en LibreChat así:

  chat-perplexity:
    type: stdio
    command: npx
    args:
      - -y
      - @pyroprompts/any-chat-completions-mcp
    env:
      AI_CHAT_KEY: "pplx-012345679"
      AI_CHAT_NAME: Perplexity
      AI_CHAT_MODEL: sonar
      AI_CHAT_BASE_URL: "https://api.perplexity.ai"
      PATH: '/usr/local/bin:/usr/bin:/bin'

Y se muestra en LibreChat:

LibreChat con chat de perplejidad

Instalación mediante herrería

Para instalar cualquier integración de API compatible con OpenAI para Claude Desktop automáticamente a través de Smithery :

npx -y @smithery/cli install any-chat-completions-mcp-server --client claude

Depuración

Dado que los servidores MCP se comunican a través de stdio, la depuración puede ser complicada. Recomendamos usar el Inspector MCP , disponible como script de paquete:

npm run inspector

El Inspector proporcionará una URL para acceder a las herramientas de depuración en su navegador.

Expresiones de gratitud

Available Tools

1 tool
chat-with-openaiC

Text chat with OpenAI

ParametersJSON Schema
NameRequiredDescriptionDefault
contentYesThe content of the chat to send to OpenAI

TDQS

C2.7/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description does not disclose any behavioral traits such as whether it is read-only, destructive, or requires authentication. The tool's side effects or limitations are unknown.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short sentence with no unnecessary words. It is concise, though it does not elaborate on details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description fails to provide essential context such as expected output, potential side effects, or error conditions. A simple chat tool still benefits from minimal completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents the lone parameter. The description adds no additional meaning beyond what the schema provides, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Text chat with OpenAI' clearly states the action (chat) and the resource (OpenAI). It is specific and distinct enough, though very brief.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool or any alternatives. No usage context or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedchat-with-openai
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.8/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools.

Naming Consistency5/5

With a single tool, naming inconsistency is not applicable; it follows a clear verb_noun pattern ('chat' + 'with-openai').

Tool Count1/5

A chat completions server should typically offer multiple tools (e.g., streaming, model listing, conversation history). A single tool feels overly minimal for the domain.

Completeness1/5

The single tool only covers basic text chat, missing obvious needs like streaming, parameter customization, or model availability queries, making the surface severely incomplete.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches